Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    čin
    -0.07
    900
    -0.07
    WOOD
    -0.07
    mse
    -0.07
     Guides
    -0.06
     mate
    -0.06
    .cpu
    -0.06
     C
    -0.06
     kisses
    -0.06
     Comm
    -0.06
    POSITIVE LOGITS
    арамет
    0.07
    _primitive
    0.06
    nist
    0.06
    .:.:.:
    0.06
    /////////////////////////////////////////////////////////////////////////////↵
    0.06
    WebResponse
    0.06
    三三三三
    0.06
    (Local
    0.06
    РА
    0.06
     Trojan
    0.05
    Act Density 0.000%

    No Known Activations